You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Putting this out there as a way to alleviate the many dependencies issues. I'll soon be shipping a PLAID (&compression, that will come later)-free indexing method, which will alleviate the need to run custom CUDA code or faiss when indexing small collections (anything up to ~2000 256 token documents can still be queried in hundreds of milliseconds on CPU).
Once this index has shipped, I am planning to overhaul dependencies, as I'm being told more and more that RAGatouille is making it into prod use cases and the "full fat" default version is kind of annoying. This is where I'm currently at in terms of versions:
REMOVE SENTENCE-TRANSFORMERS Features: Training, hard negative mining Additional deps:
Voyager (hard neg dense quick retrieval)
ragatouille[plaid-cpu]
Features: Plaid indexing on CPU AdditionalDeps:
faiss-cpu
llama-index (for now, for chunking)
ragatouille[plaid-gpu]
Features: Plaid indexing on GPU AdditionalDeps:
faiss-gpu
llama-index (for now, for chunking)
ragatouille[langchain]
Features: Allows export as langchain retriever AdditionalDeps:
langchain
langchain_core
ragatouille[onnx]
Features: Allows ONNX format export (for Vespa) AdditionalDeps:
onnx
ragatouille[all]
Features: Everything Deps:
all of the above
Any feedback on this would be appreciated at this stage -- very early thoughts still! One big question is whether torch (which is required) should ship with the base version, or be optional to facilitate env compatibility.
The text was updated successfully, but these errors were encountered:
There are issues when adding ragatouille to a llama-index 0.10.x project. It pulls an 0.9.x artifact and some of the core namespaces get confused, e.g. you can't import LLM from core anymore. Since it doesn't seem integral to your project, perhaps you could bump it up.
Putting this out there as a way to alleviate the many dependencies issues. I'll soon be shipping a PLAID (&compression, that will come later)-free indexing method, which will alleviate the need to run custom CUDA code or
faiss
when indexing small collections (anything up to ~2000 256 token documents can still be queried in hundreds of milliseconds on CPU).Once this index has shipped, I am planning to overhaul dependencies, as I'm being told more and more that RAGatouille is making it into prod use cases and the "full fat" default version is kind of annoying. This is where I'm currently at in terms of versions:
ragatouille
Features: Search, In-memory encoding, uncompressed indexing
Deps:
ragatouille[train]
REMOVE SENTENCE-TRANSFORMERS
Features: Training, hard negative mining
Additional deps:
ragatouille[plaid-cpu]
Features: Plaid indexing on CPU
Additional Deps:
ragatouille[plaid-gpu]
Features: Plaid indexing on GPU
Additional Deps:
ragatouille[langchain]
Features: Allows export as langchain retriever
Additional Deps:
ragatouille[onnx]
Features: Allows ONNX format export (for Vespa)
Additional Deps:
ragatouille[all]
Features: Everything
Deps:
Any feedback on this would be appreciated at this stage -- very early thoughts still! One big question is whether
torch
(which is required) should ship with the base version, or be optional to facilitate env compatibility.The text was updated successfully, but these errors were encountered: